Perplexity launches Orchestrator API: 45+ models, auto-routing, unified billing
perplexity_ai · x · 2026-11-18
Perplexity announced the Orchestrator API, giving developers unified access to a cross-vendor model layer:
- Serves 45+ models from OpenAI, Anthropic, Google, xAI plus open-weight models, picking the right model per task and auto-selecting providers by availability, capacity, and latency
- Automatic routing (preview) maps plain-language tasks to models via profiles, then uses a decision model to match conversations to routes
- Works with existing OpenAI/Anthropic SDKs, supporting Chat Completions, Responses, and Anthropic Messages APIs
- Built on Perplexity's production model layer, which routes hundreds of millions of requests daily across 85+ models and a dozen providers
- Billing at each model's published per-token rate, with spend tracking by model/project/key, model allowlists, and spend caps
More from coding & agent
- Neon MCP Has Double the DAU of Its CLI Despite All Efforts Pushing CLI — JensHonack · 2026-11-18
- OpenAI's Agent-Swarm Playbook for Boring Spark Upgrades, Shown at QCon — AdiPolak · 2026-11-18
- Orthogonal Launches Data Marketplace for Agents With 100+ Per-Call Data Providers — ycombinator · 2026-11-18
- Replit CEO on Missions: an Agentic Swarm Harness That Hits Goals Within Budget — amasad · 2026-11-18
- User says he'd pay $20/month extra for an X API that lets agents read posts — willdepue · 2026-11-18
- HF CEO: RL-Adapted Qwen3.8-27B Doubles SWE-bench Pro Score to 62.7% for pi Agent — victormustar · 2026-11-18